CN115935250A - Fault diagnosis method and system based on differential oscillator and domain adaptive hybrid model - Google Patents
Fault diagnosis method and system based on differential oscillator and domain adaptive hybrid model Download PDFInfo
- Publication number
- CN115935250A CN115935250A CN202211406975.5A CN202211406975A CN115935250A CN 115935250 A CN115935250 A CN 115935250A CN 202211406975 A CN202211406975 A CN 202211406975A CN 115935250 A CN115935250 A CN 115935250A
- Authority
- CN
- China
- Prior art keywords
- model
- differential
- fault
- differential oscillator
- adaptive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 25
- 238000010587 phase diagram Methods 0.000 claims abstract description 85
- 239000003245 coal Substances 0.000 claims abstract description 29
- 230000007246 mechanism Effects 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 230000000739 chaotic effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the field of fault diagnosis of coal equipment, in particular to a fault intelligent diagnosis method based on a differential oscillator and a field adaptive hybrid model, which comprises the following steps: establishing a differential oscillator output phase diagram data sample set, and establishing a domain self-adaptive model by adopting a maximum mean difference principle; determining the characteristics of equipment faults by utilizing a coal machine equipment fault mechanism model; setting detection characteristics and other parameters of the differential oscillator according to the fault characteristics; preprocessing the acquired vibration signals by using a filtering technology, and inputting the preprocessed vibration signals into a differential oscillator model; and (4) inputting the output result of the differential oscillator model into the trained intelligent model as an input quantity for fault classification and identification. The invention utilizes the characteristic that the differential oscillator can effectively detect nonlinear and non-stationary signals to carry out differential transformation on the acquired vibration signals. After differential transformation, the phase diagrams are diversified, and intelligent identification of the state of the phase diagrams is realized by utilizing a domain self-adaptive method.
Description
Technical Field
The invention relates to the field of fault diagnosis of coal mining equipment, in particular to a fault diagnosis method and system based on a differential oscillator and a field adaptive hybrid model.
Background
With the increasing level of intellectualization of coal equipment, especially the rising of hot tide in smart mine construction, people reduction, efficiency improvement and safety increase become important indexes for measuring the smart mine construction effect. In order to ensure safe and reliable operation of coal mining equipment, intelligent diagnosis of the state of the coal mining equipment becomes a main component of intelligent mine construction. Due to the fact that the coal machine equipment is greatly influenced by the environment (impact, dustiness and humidity) due to special working conditions, the application of the intelligent coal machine equipment diagnosis technology in the field of coal machines is severely restricted by factors such as variable superposition working conditions, variable loads, lack of effective data samples on site and the like.
The difficulty of characteristic frequency extraction is caused by the fact that the special equipment of the coal mine is changeable in operation environment and working condition and changeable in load. The traditional feature extraction method and technology mainly aim at a specific problem, a fault diagnosis expert needs to deeply know the running state features of equipment, a signal processing method is used for feature extraction and identification, the requirement on personnel is high, and the method and the technology are not suitable for being popularized and applied in a coal mine site.
In the actual operation process of the coal machine equipment, the production task is mainly completed, so that the acquired data is mainly health data in normal operation. When an actual device fails, sufficient data cannot be extracted and collected in many cases. At the same time, the cost of collecting sample data for each type of equipment failure exclusively in the field is often unacceptable. Compared with a laboratory fault simulation experiment, the fault of the field coal machine equipment has randomness, and the feature distribution of training and testing data acquired under different working conditions and loads also has drift, so that the application of intelligent diagnosis methods based on a data-driven Support Vector Machine (SVM), a recurrent neural network and the like in the field of coal machines is restricted from two aspects of fault sample data and fault sample types.
Chinese patent CN201010561227.5 discloses a method for extracting weak features of early faults of a high-speed wire rolling mill, however, the technical scheme is only to detect single frequency of faults and does not relate to multi-fault frequency detection; in addition, the technical scheme carries out phase diagram identification by calculating the point number of the designated area, and is suitable for field application scenes with constant load and working condition without relating to field actual application scenes such as variable working condition, variable load and the like.
Chinese patent CN201611164942.9 discloses an amplitude detection method for weak vibration signals of a gantry crane, however, the core of the technical solution is that a reference signal is introduced to determine the amplitude and phase of the detection frequency in the original signal, and for the determination of the signal amplitude, the size of the detection frequency amplitude is determined by the side length of an inscribed square, the scheme is complex, and the detection accuracy is low.
Chinese patent CN201710073526.6 discloses a nonlinear fault prediction method for electromechanical devices, but the core of the technical scheme is that a hybrid model of stochastic resonance and chaotic oscillators is used to realize the detection of weak signals, a phase diagram state of the chaotic oscillators is described by using p + q order moments, the p + q order moments are used as a threshold for interpreting the phase diagram state of the chaotic oscillators, and the intellectualization and efficiency of identification are extremely low.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides a fault diagnosis method and a fault diagnosis system based on a differential oscillator and a field self-adaptive hybrid model, and the invention has the advantages that the characteristic that the differential oscillator can effectively detect nonlinear and non-stationary signals is utilized, and differential transformation is carried out on the acquired vibration signals; after differential transformation, the phase diagrams are diversified, and intelligent identification of the phase diagram state is realized by utilizing a domain self-adaptive method.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a fault diagnosis method based on a differential oscillator and a field self-adaptive hybrid model, which comprises the following steps:
s1, constructing a differential oscillator output phase diagram data sample set, wherein the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of a differential oscillator phase diagram;
s2, establishing a field self-adaptive model, and training the field self-adaptive model by using the phase diagram data sample set so as to obtain a trained field self-adaptive model, wherein the trained field self-adaptive model is used for identifying the state of a phase diagram output by a differential oscillator under an actual working condition, so that intelligent fault diagnosis is realized;
s3, determining the characteristics of the equipment fault by using an equipment fault mechanism model;
s4, setting parameters of the differential oscillator based on the characteristics of the equipment faults, wherein the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator transformation sequence and detect the possible fault characteristics of the equipment one by one;
and S5, carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
Preferably, the two types of phase diagrams of the differential oscillator phase diagram in S1 include a polar ring state phase diagram and a pole state phase diagram, wherein the polar ring state and the pole state both include a plurality of different forms; the pole ring state phase diagram representation contains fault signatures and the pole state phase diagram representation does not contain monitored fault information.
Preferably, the adaptive model in the S2 domain is established based on the maximum mean difference principle.
Preferably, the characteristics of equipment failure in S3 include bearing failure characteristics, gear failure characteristics and/or crack failure characteristics.
Preferably, the differential oscillator model in S4 is that one or more differential oscillators are constructed according to the characteristics of the fault mechanism model, and a differential oscillator transformation sequence is formed to detect the fault characteristics possibly existing in the coal equipment one by one.
Preferably, the S5 includes:
s51, preprocessing the acquired vibration signals by using a filtering technology; the filtering technology is used for filtering, so that the signal-to-noise ratio of a signal is improved, and the noise interference of a phase diagram after the differential oscillator is converted is reduced;
s52, inputting the preprocessed vibration signal into a differential vibrator model;
and S53, inputting the output result of the differential oscillator model into a domain self-adaptive model as an input quantity for fault classification and identification.
Preferably, the filtering technique of S51 is autocorrelation filtering or adaptive particle swarm filtering.
The second aspect of the present invention provides a fault diagnosis system based on a differential oscillator and a domain adaptive hybrid model, including:
the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of a differential oscillator phase diagram;
the system comprises a domain self-adaptive establishing module, a phase diagram data sample set and a phase diagram output module, wherein the domain self-adaptive establishing module is used for establishing a domain self-adaptive model and training the domain self-adaptive model by using the phase diagram data sample set so as to obtain a trained domain self-adaptive model, and the trained domain self-adaptive model is used for identifying the state of a differential oscillator output phase diagram under an actual working condition so as to realize intelligent fault diagnosis;
the equipment fault characteristic determining module is used for determining the characteristics of the equipment fault by utilizing an equipment fault mechanism model;
the differential oscillator parameter setting module is used for setting parameters of the differential oscillator based on the characteristics of the equipment faults, and the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator transformation sequence and detect the possible fault characteristics of the equipment one by one;
and the fault diagnosis module is used for carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
A third aspect of the invention provides an electronic device comprising a processor and a memory, the memory storing a plurality of instructions, the processor being configured to read the instructions and to perform the method according to the first aspect.
A fourth aspect of the invention provides a computer readable storage medium storing a plurality of instructions readable by a processor and performing the method of the first aspect.
The method, the device, the electronic equipment and the computer readable storage medium provided by the invention have the following beneficial technical effects:
1. the invention adopts the differential oscillator and the field adaptive hybrid model, and has the core that the diagnosis of the running state of the coal machine equipment under the variable working condition and the variable load working condition is realized through the differential oscillator and the neighborhood adaptive hybrid model, thereby overcoming the influence of the special working condition and the lack of effective data samples of the coal machine on the intelligent diagnosis result, and realizing the intelligent diagnosis of the fault of the coal machine equipment under the variable working condition and the variable load condition.
2. The data sample set is established on the basis of field actual measurement signals, and a foundation is laid for solving the field practical problem of the model.
3. The invention establishes the relation between the mechanism model and the actual use working condition of the coal machine equipment, provides a path for the application and practice of the mechanism model, and simultaneously has small calculation amount of the mixed model and easy integration in software and hardware.
4. The detection frequency is determined according to a mechanism model, and a differential oscillator array is formed by utilizing a series of differential oscillators) so as to realize the detection of multiple faults, rather than detecting the single frequency of the fault; the complexity of recognizing the phase diagram by calculating the number of points in the designated area is overcome, and the automatic recognition of the phase diagram is realized by utilizing the field self-adaptive technology; the applicable object extends from the field application scene with constant load and working condition to the field actual application scene with variable working condition, variable load and the like.
5. The invention realizes the identification of the phase diagram state of the differential oscillator by using the neighborhood adaptive technology, is an intelligent identification method and improves the identification efficiency.
6. The defect that a traditional hybrid model is adopted for weak signal identification is overcome, and particularly the defect that the detection frequency is determined by using stochastic resonance and the p + q order moment is used as a threshold value for phase diagram judgment, and the defect that the detection frequency is not black or white is overcome; the detection frequency is determined by utilizing a mechanism model, the field self-adaptive model is adopted, the differential oscillator identification under the variable working condition and the variable load condition is realized, and the method is an intelligent identification technology and is more suitable for the modern field application scene.
Drawings
FIG. 1 is a flow chart of differential oscillator and domain adaptive hybrid model fault intelligent diagnosis according to a preferred embodiment of the present invention;
FIG. 2 is a sample set of differential oscillator phase diagram data according to a preferred embodiment of the present invention;
FIG. 3 is a diagram illustrating the output result after conversion of the differential oscillator according to the preferred embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to a preferred embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments of the present invention.
Example one
As shown in fig. 1, a fault diagnosis method based on a differential oscillator and a domain adaptive hybrid model includes the following steps:
s1, constructing a differential oscillator output phase diagram data sample set, wherein the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of a differential oscillator phase diagram;
s2, establishing a field self-adaptive model, and training the field self-adaptive model by using the phase diagram data sample set so as to obtain a trained field self-adaptive model, wherein the trained field self-adaptive model is used for identifying the state of a phase diagram output by a differential oscillator under an actual working condition, so that intelligent fault diagnosis is realized;
s3, determining the characteristics of the equipment fault by using an equipment fault mechanism model; the equipment in the embodiment is a coal machine, wherein a failure mechanism model of the coal machine equipment belongs to a part in the prior art, and is not described herein again;
s4, setting parameters of the differential oscillator based on the characteristics of the equipment faults, wherein the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator conversion sequence and detect the fault characteristics possibly existing in the equipment one by one;
and S5, carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
As a preferred embodiment, the two types of phase diagrams of the differential oscillator phase diagram in S1 include a polar ring state phase diagram and a pole state phase diagram, where the polar ring state and the pole state both include a plurality of different forms; the pole ring state phase diagram representation contains fault signatures and the pole state phase diagram representation does not contain monitored fault information.
As a preferred embodiment, the domain adaptive model in S2 is established based on the principle of maximum mean difference.
In a preferred embodiment, the characteristics of the equipment failure in S3 include a bearing failure characteristic, a gear failure characteristic and/or a crack failure characteristic.
As a preferred embodiment, the differential oscillator model in S4 is to construct one or more differential oscillators according to the characteristics of the fault mechanism model, and form a differential oscillator transformation sequence to detect the possible fault characteristics of the coal equipment one by one.
As a preferred embodiment, the S5 includes:
s51, preprocessing the acquired vibration signals by using a filtering technology; the filtering technology is used for filtering, so that the signal-to-noise ratio of a signal is improved, and the noise interference of a phase diagram after the differential oscillator is converted is reduced;
s52, inputting the preprocessed vibration signal into a differential vibrator model;
and S53, inputting the output result of the differential oscillator model into a domain self-adaptive model as an input quantity for fault classification and identification.
As a preferred implementation, the filtering technique of S51 is autocorrelation filtering or adaptive particle swarm filtering.
In a specific application scenario of a coal machine, the intelligent fault diagnosis method based on the differential oscillator and the field adaptive hybrid model provided by the embodiment includes the following steps:
step 1, establishing a differential oscillator phase diagram data set by using field measured data. Acquiring a large number of data samples from the site, setting the detection frequency of the differential oscillator, and inputting the data samples into the differential oscillator to obtain a differential oscillator phase diagram. The obtained differential oscillator phase diagram mainly comprises two types: one type is the polar ring state, which indicates the presence of a detected fault signature in the signal. One type is a pole state, indicating the absence of a detected fault signature in the signal. Due to the special working condition environment of the site of the coal equipment and the operation characteristics of the coal equipment, the differential oscillator phase diagram output is not in a standard form, as shown in figure 2. Here a data set is established containing a source domain with a label and an unlabeled target domain.
Step 2, establishing a domain self-adaptive model by adopting a maximum mean difference principle, and carrying out model training to obtain the subsequent domain self-adaptive model which can be used for fault intelligent diagnosis, wherein in the diagnosis process, a differential oscillator phase diagram obtained in real time is input into a feedforward network feature extraction module for feature extraction; the classifier is then entered to classify the results of the feature extraction, here there are two and only two classes, namely the pole state and the polar ring state.
Step 3, the adopted example is an intelligent diagnosis example of the motor fault of the main belt conveyor of the mine main well. According to a fault mechanism model, the motor has the characteristics of 4 faults, such as misalignment fault, foundation bolt loosening fault, rotor support bearing fault, rotor collision and abrasion fault and the like.
And 4, respectively establishing a differential oscillator model aiming at the 4 fault characteristics, setting parameters of the differential oscillator model, and detecting corresponding fault characteristics.
Let the signal to be detected be T (k), the differential oscillator-based detector is as follows:
x k+1 ＝ax k +by k
y k+1 ＝cx k +dy k +p·cos(2kπf e +2kπf d /fs)·T(k)
wherein p is a magnification factor, f e Is the system excitation frequency, f d Is to detect a fault signature, f s Is the sampling frequency.
The input of the differential oscillator is shown in fig. 3, and as known by the differential oscillator detector, the output of the differential oscillator is composed of two terms, and the two terms are respectively used as x-axis coordinates and y-axis coordinates, so that a differential oscillator output phase diagram is constructed.
And 5, inputting the acquired vibration signals of the motor into the differential oscillator model respectively. And inputting the obtained differential oscillator phase diagram into a trained field self-adaptive model to realize intelligent identification of the state of the coal equipment.
Intelligent diagnosis result of motor fault of main belt conveyor
Through intelligent identification, the motor can be judged to have the misalignment fault symptom, namely the motor has the misalignment fault. Through inspection, the coaxiality error of the output shaft of the motor and the input shaft of the connected equipment seriously exceeds the standard, the misalignment fault is caused, and the inspection result is in accordance with the actual field.
Example two
A fault diagnosis system based on a differential oscillator and a domain adaptive hybrid model comprises:
the data sample set construction module is used for constructing a phase diagram data sample set output by the differential oscillator, the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of the differential oscillator phase diagram;
the system comprises a domain self-adaptive establishing module, a phase diagram data sample set and a phase diagram output module, wherein the domain self-adaptive establishing module is used for establishing a domain self-adaptive model and training the domain self-adaptive model by using the phase diagram data sample set so as to obtain a trained domain self-adaptive model, and the trained domain self-adaptive model is used for identifying the state of a differential oscillator output phase diagram under an actual working condition so as to realize intelligent fault diagnosis;
the equipment fault characteristic determining module is used for determining the characteristics of the equipment fault by utilizing an equipment fault mechanism model; the equipment in the embodiment is a coal machine, wherein a failure mechanism model of the coal machine equipment belongs to a part in the prior art, and is not described herein again;
the differential oscillator parameter setting module is used for setting parameters of the differential oscillator based on the characteristics of the equipment faults, and the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator conversion sequence and detect the fault characteristics possibly existing in the equipment one by one;
and the fault diagnosis module is used for carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
The present invention also provides a memory storing a plurality of instructions for implementing the method according to embodiment one.
As shown in fig. 4, the present invention further provides an electronic device, which includes a processor 301 and a memory 302 connected to the processor 301, where the memory 302 stores a plurality of instructions, and the instructions can be loaded and executed by the processor, so that the processor can execute the method according to the first embodiment.
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (10)
1. A fault diagnosis method based on a differential oscillator and a domain adaptive hybrid model is characterized by comprising the following steps:
s1, constructing a differential oscillator output phase diagram data sample set, wherein the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of a differential oscillator phase diagram;
s2, establishing a field self-adaptive model, and training the field self-adaptive model by using the phase diagram data sample set so as to obtain a trained field self-adaptive model, wherein the trained field self-adaptive model is used for identifying the state of a phase diagram output by a differential oscillator under an actual working condition, so that intelligent fault diagnosis is realized;
s3, determining the characteristics of the equipment fault by using an equipment fault mechanism model;
s4, setting parameters of the differential oscillator based on the characteristics of the equipment faults, wherein the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator transformation sequence and detect the possible fault characteristics of the equipment one by one;
and S5, carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
2. The fault diagnosis method based on the differential oscillator and the domain adaptive hybrid model is characterized in that the two types of phase diagrams of the differential oscillator phase diagram in the S1 comprise a polar ring state phase diagram and a pole state phase diagram, wherein the polar ring state and the pole state comprise various different forms; the pole ring state phase diagram representation contains a fault signature and the pole state phase diagram representation does not contain monitored fault information.
3. The method for fault diagnosis based on the differential oscillator and the domain adaptive hybrid model according to claim 2, wherein the domain adaptive model in S2 is established based on a maximum mean difference principle.
4. The fault diagnosis method based on the differential oscillator and the domain adaptive hybrid model is characterized in that the characteristics of the equipment fault in the S3 comprise bearing fault characteristics, gear fault characteristics and/or crack fault characteristics.
5. The fault diagnosis method based on the differential vibrators and the field adaptive hybrid model is characterized in that the differential vibrator model in the S4 is that one or more differential vibrators are constructed according to the characteristics of a fault mechanism model to form a differential vibrator conversion sequence to detect the possible fault characteristics of coal machine equipment one by one.
6. The fault diagnosis method based on the differential oscillator and the domain adaptive hybrid model according to claim 5, wherein the step S5 comprises:
s51, preprocessing the acquired vibration signals by using a filtering technology; the filtering technology is used for filtering, so that the signal-to-noise ratio of a signal is improved, and the noise interference of a phase diagram after the differential oscillator is converted is reduced;
s52, inputting the preprocessed vibration signals into a differential vibrator model;
and S53, inputting the output result of the differential oscillator model into a domain self-adaptive model as an input quantity for fault classification and identification.
7. The method according to claim 6, wherein the filtering technique of S51 is autocorrelation filtering or adaptive particle swarm filtering.
8. A fault diagnosis system based on a differential oscillator and a domain adaptive hybrid model is characterized by comprising:
the phase diagram data sample set comprises a source domain and a target domain, and the phase diagram data sample set covers two types of phase diagrams of a differential oscillator phase diagram;
the domain self-adaptive establishing module is used for establishing a domain self-adaptive model and training the domain self-adaptive model by using the phase diagram data sample set so as to obtain a trained domain self-adaptive model, and the trained domain self-adaptive model is used for identifying the state of the differential oscillator output phase diagram under the actual working condition so as to realize intelligent fault diagnosis;
the equipment fault characteristic determining module is used for determining the characteristic of the equipment fault by utilizing the equipment fault mechanism model;
the differential oscillator parameter setting module is used for setting parameters of the differential oscillator based on the characteristics of the equipment faults, and the parameters comprise detection characteristics of the differential oscillator; establishing a differential oscillator model based on parameters of differential oscillators, wherein the differential oscillator model is used for constructing one or more differential oscillators according to the characteristics of an equipment fault mechanism model, and the differential oscillators form a differential oscillator transformation sequence and detect the possible fault characteristics of the equipment one by one;
and the fault diagnosis module is used for carrying out fault diagnosis based on the domain self-adaptive model and the differential oscillator model.
9. An electronic device comprising a processor and a memory, the memory storing a plurality of instructions, the processor configured to read the instructions and perform the method of any of claims 1-7.
10. A computer-readable storage medium storing a plurality of instructions readable by a processor and performing the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406975.5A CN115935250B (en) | 2022-11-10 | 2022-11-10 | Fault diagnosis method and system based on differential vibrator and field self-adaptive hybrid model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406975.5A CN115935250B (en) | 2022-11-10 | 2022-11-10 | Fault diagnosis method and system based on differential vibrator and field self-adaptive hybrid model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115935250A true CN115935250A (en) | 2023-04-07 |
| CN115935250B CN115935250B (en) | 2023-10-27 |
Family
ID=86552976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211406975.5A Active CN115935250B (en) | 2022-11-10 | 2022-11-10 | Fault diagnosis method and system based on differential vibrator and field self-adaptive hybrid model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115935250B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972989A (en) * | 2023-12-28 | 2024-05-03 | 天地(常州)自动化股份有限公司北京分公司 | Service life prediction method and system for coal machine equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102059255A (en) * | 2010-11-23 | 2011-05-18 | 首钢总公司 | Early fault weak characteristic extracting method for high speed wire rolling mill |
| CN112633339A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Bearing fault intelligent diagnosis method, bearing fault intelligent diagnosis system, computer equipment and medium |
| CN114429150A (en) * | 2021-12-30 | 2022-05-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under variable working conditions based on improved depth subdomain adaptive network |
| CN115096626A (en) * | 2022-06-13 | 2022-09-23 | 煤炭科学研究总院有限公司 | Method and device for detecting failure frequency of coal machine equipment, electronic equipment and medium |
| US20220327035A1 (en) * | 2020-06-03 | 2022-10-13 | Soochow University | Intra-class adaptation fault diagnosis method for bearing under variable working conditions |
-
2022
- 2022-11-10 CN CN202211406975.5A patent/CN115935250B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102059255A (en) * | 2010-11-23 | 2011-05-18 | 首钢总公司 | Early fault weak characteristic extracting method for high speed wire rolling mill |
| US20220327035A1 (en) * | 2020-06-03 | 2022-10-13 | Soochow University | Intra-class adaptation fault diagnosis method for bearing under variable working conditions |
| CN112633339A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Bearing fault intelligent diagnosis method, bearing fault intelligent diagnosis system, computer equipment and medium |
| CN114429150A (en) * | 2021-12-30 | 2022-05-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under variable working conditions based on improved depth subdomain adaptive network |
| CN115096626A (en) * | 2022-06-13 | 2022-09-23 | 煤炭科学研究总院有限公司 | Method and device for detecting failure frequency of coal machine equipment, electronic equipment and medium |
Non-Patent Citations (2)
| Title |
|---|
| 李静雅;魏红;: "基于相关差分振子阵列的煤矿电机故障诊断研究", 太原科技大学学报, no. 03 * |
| 马海龙;李臻;朱益军;陈思安;: "基于差分振子的带式输送机故障诊断方法", 工矿自动化, no. 10 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972989A (en) * | 2023-12-28 | 2024-05-03 | 天地(常州)自动化股份有限公司北京分公司 | Service life prediction method and system for coal machine equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115935250B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110768B (en) | Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers | |
| CN102621150B (en) | Airplane skin damage identification method based on gray level co-occurrence matrix and support vector machine | |
| CN103115789B (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
| CN115688018A (en) | Method for monitoring state and diagnosing fault of bearing under multiple working conditions | |
| CN109612729A (en) | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings | |
| CN103496625B (en) | Multi-rope friction lifter load identification method based on vibration analysis | |
| CN113128555B (en) | Method for detecting abnormality of train brake pad part | |
| CN110060368A (en) | Mechanical method for detecting abnormality based on potential feature coding | |
| Shajihan et al. | CNN based data anomaly detection using multi-channel imagery for structural health monitoring | |
| CN115935250A (en) | Fault diagnosis method and system based on differential oscillator and domain adaptive hybrid model | |
| Shubita et al. | Fault detection in rotating machinery based on sound signal using edge machine learning | |
| CN105160359A (en) | Complex structure damage cooperative identification method based on ultrasonic guided-wave | |
| CN115238785A (en) | Rotary machine fault diagnosis method and system based on image fusion and integrated network | |
| De Lima et al. | On fault classification in rotating machines using fourier domain features and neural networks | |
| CN111582135B (en) | Excavator hand operation proficiency evaluation method and device based on working stage identification | |
| CN113869339A (en) | Deep learning classification model for fault diagnosis and fault diagnosis method | |
| CN115526515A (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| Soleimani-Babakamali et al. | Zero-shot transfer learning for structural health monitoring using generative adversarial networks and spectral mapping | |
| CN118130984A (en) | Cable partial discharge fault real-time monitoring method based on data driving | |
| Li et al. | Intelligent fault diagnosis of aeroengine sensors using improved pattern gradient spectrum entropy | |
| CN106909136A (en) | A kind of method for diagnosing faults based on index regularization kernel linear discriminant analysis | |
| CN116466408B (en) | Artificial neural network superbedrock identification method based on aeromagnetic data | |
| CN110197120B (en) | Personnel target identification method for unattended sensor system | |
| CN109459489A (en) | A kind of elevator crack detecting method based on Magnetic memory testing principle | |
| CN114118166A (en) | Transformer fault diagnosis system and method based on intelligent frequency spectrum monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |